activity
20242026
collaborators

9 papers

cs.CR2026

Dr. Jekyll and Mr. Hyde: Two Faces of LLMs

Matteo Gioele Collu, Tom Janssen-Groesbeek, Stefanos Koffas +2

Large Language Models (LLMs) are being integrated into applications such as chatbots or email assistants. To prevent improper responses, safety mechanisms, such as Reinforcement Le…

cs.CR2026

Backdoor Attacks on Decentralised Post-Training

Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training c…

cs.CV2026

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors

Gorka Abad, Ermes Franch, Stefanos Koffas +1

Current backdoor defenses assume that neutralizing a known trigger removes the backdoor. We show this trigger-centric view is incomplete: \emph{alternative triggers}, patterns perc…

cs.CR2025

Towards Backdoor Stealthiness in Model Parameter Space

Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas +1

Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent…

cs.CR2025

SoK: The Last Line of Defense: On Backdoor Defense Evaluation

Gorka Abad, Marina Krček, Stefanos Koffas +7

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been…

cs.LG2025

CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding

Behrad Tajalli, Stefanos Koffas, Stjepan Picek

Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as…